Model comparison
Claude 3 Sonnet vs DeepSeek-R1
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeekSummary
- They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and DeepSeek-R1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 43.8 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 96.6% for DeepSeek-R1.
Side by side
| Claude 3 Sonnet | DeepSeek-R1 | |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 29.0 | 42.3 |
| Released | 2024-02-29 | 2025-01-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 164K |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.15 |
| Results tracked | 30 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
Claude 3 Sonnet: 29.6 (#302), DeepSeek-R1: 46.3 (#68)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| WeirdML | 10.2% | 41.6% |
| LMArena Coding | 1223 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| BigCodeBench Instruct | 42.7% | — |
| LiveBench Coding | — | 66.7% |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, DeepSeek-R1: 30.7 (#75)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 20.5 (#237), DeepSeek-R1: 18.6 (#278)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1416 |
| Epoch Capabilities Index | 120.7 | 141.29 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | — | 83.2% |
| DTBench | 53.6% | — |
| LiveBench Data Analysis | — | 69.8% |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |
| WinoGrande | 75.1% | — |
Math DeepSeek-R1 leads
Claude 3 Sonnet: 10.7 (#310), DeepSeek-R1: 43.8 (#79)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 66.4% |
| LMArena Math | 1213 | 1400 |
| MATH Level 5 | 18.2% | 96.6% |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
Knowledge DeepSeek-R1 leads
Claude 3 Sonnet: 21.1 (#276), DeepSeek-R1: 44.5 (#87)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | 40.6% | 76.3% |
| LMArena Expert | 1173 | 1394 |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 25.2 (#125), DeepSeek-R1: —
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual DeepSeek-R1 leads
Claude 3 Sonnet: 37.8 (#234), DeepSeek-R1: 52.4 (#85)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1205 | 1412 |
| LMArena Chinese | 1189 | 1442 |
| LMArena French | 1229 | 1417 |
| LMArena German | 1204 | 1404 |
| LMArena Japanese | 1131 | 1391 |
| LMArena Korean | 1128 | 1360 |
| LMArena Russian | 1227 | 1423 |
| LMArena Spanish | 1204 | 1411 |
Instruction Following DeepSeek-R1 leads
Claude 3 Sonnet: 62.8 (#235), DeepSeek-R1: 72.0 (#143)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1199 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |
Long Context DeepSeek-R1 leads
Claude 3 Sonnet: 36.7 (#228), DeepSeek-R1: 45.4 (#36)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1211 | 1391 |
| Fiction.LiveBench | — | 75% |
Writing & Preference DeepSeek-R1 leads
Claude 3 Sonnet: 42.1 (#238), DeepSeek-R1: 61.4 (#88)
| Benchmark | Claude 3 Sonnet | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1218 | 1428 |
| LMArena Creative Writing | 1186 | 1405 |
| LMArena Multi-Turn | 1227 | 1405 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1500 |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |
Frequently asked questions
Is Claude 3 Sonnet better than DeepSeek-R1?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or DeepSeek-R1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and DeepSeek-R1 share?
22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek-R1 has 52.